FazBrowse GitHub Viewer
|
Trending
|
URL:
|
Home
Tools:
[Download Repo ZIP]
[View Raw Code]
[Original HTTPS Page]
gpython/parser/lexer.go at master · xarus01/gpython · GitHub
xarus01
/
gpython
Public
forked from
go-python/gpython
Notifications
You must be signed in to change notification settings
Fork
0
Star
0
Code
Pull requests
0
Actions
Projects
Security and quality
0
Insights
Additional navigation options
Code
Pull requests
Actions
Projects
Security and quality
Insights
Expand file tree
Breadcrumbs
gpython
/
parser
/
lexer.go
Copy path
More file actions
More file actions
Latest commit
History
History
History
989 lines (922 loc) · 22.3 KB
Breadcrumbs
gpython
/
parser
/
lexer.go
Copy path
File metadata and controls
989 lines (922 loc) · 22.3 KB
Raw
Copy raw file
Download raw file
Open symbols panel
Edit and raw actions
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
// Copyright 2018 The go-python Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
package
parser
// FIXME need to implement formfeed
// Lexer should count line numbers too!
import
(
"bufio"
"bytes"
"fmt"
"io"
"log"
"regexp"
"strings"
"unicode"
"github.com/go-python/gpython/ast"
"github.com/go-python/gpython/py"
)
// The parser expects the lexer to return 0 on EOF. Give it a name
// for clarity.
const
eof
=
0
// Signal eof with Error
const
eofError
=
-
1
// Standard python definition of a tab
const
tabSize
=
8
// The parser uses the type <prefix>Lex as a lexer. It must provide
// the methods Lex(*<prefix>SymType) int and Error(string).
type
yyLex
struct
{
reader
*
bufio.
Reader
filename
string
// name of the file being read
line
string
// current line being parsed
lastLine
string
// last line that was parsed
pos
ast.
Pos
// current position within file
yylval
*
yySymType
// last token
eof
bool
// flag to show EOF was read
error
bool
// set if an error has ocurred
errorString
string
// the string of the error
indentStack
[]
int
// indent stack to control INDENT / DEDENT tokens
state
int
// current state of state machine
currentIndent
string
// whitespace at start of current line
interactive
bool
// set if mode "single" reading interactive input
exec
bool
// set if mode "exec" reading from file
bracket
int
// number of open [ ]
parenthesis
int
// number of open ( )
brace
int
// number of open { }
mod
ast.
Mod
// output
tokens
[]
int
// buffered tokens to output
}
// Create a new lexer
//
// The mode argument specifies what kind of code must be compiled; it
// can be 'exec' if source consists of a sequence of statements,
// 'eval' if it consists of a single expression, or 'single' if it
// consists of a single interactive statement
func
NewLex
(
r
io.
Reader
,
filename
string
,
mode
string
) (
*
yyLex
,
error
) {
x
:=
&
yyLex
{
reader
:
bufio
.
NewReader
(
r
),
filename
:
filename
,
indentStack
: []
int
{
0
},
state
:
readString
,
}
switch
mode
{
case
"exec"
:
x
.
queue
(
FILE_INPUT
)
x
.
exec
=
true
case
"eval"
:
x
.
queue
(
EVAL_INPUT
)
case
"single"
:
x
.
queue
(
SINGLE_INPUT
)
x
.
interactive
=
true
default
:
return
nil
,
py
.
ExceptionNewf
(
py
.
ValueError
,
"compile mode must be 'exec', 'eval' or 'single'"
)
}
return
x
,
nil
}
// queue tokens for later return
func
(
x
*
yyLex
)
queue
(
tokens
...
int
) {
x
.
tokens
=
append
(
x
.
tokens
,
tokens
...
)
}
// Return whether the token queue is empty
func
(
x
*
yyLex
)
queueEmpty
()
bool
{
return
len
(
x
.
tokens
)
==
0
}
// dequeue a token for return
//
// panic if no token available
func
(
x
*
yyLex
)
dequeue
()
int
{
if
x
.
queueEmpty
() {
panic
(
"token queue empty"
)
}
token
:=
x
.
tokens
[
0
]
x
.
tokens
=
x
.
tokens
[
1
:]
return
token
}
// Refill line
func
(
x
*
yyLex
)
refill
() {
var
err
error
x
.
line
,
err
=
x
.
reader
.
ReadString
(
'\n'
)
if
yyDebug
>=
2
{
fmt
.
Printf
(
"line = %q, err = %v
\n
"
,
x
.
line
,
err
)
}
x
.
pos
.
Lineno
+=
1
x
.
pos
.
ColOffset
=
0
switch
err
{
case
nil
:
case
io
.
EOF
:
x
.
eof
=
true
default
:
x
.
eof
=
true
x
.
SyntaxErrorf
(
"Error reading input: %v"
,
err
)
}
// If this is exec input, add a newline to the end of the
// string if there isn't one already.
if
x
.
eof
&&
x
.
exec
&&
len
(
x
.
line
)
>
0
&&
x
.
line
[
len
(
x
.
line
)
-
1
]
!=
'\n'
{
x
.
line
+=
"
\n
"
}
x
.
lastLine
=
x
.
line
}
// Finds the length of a space and tab seperated string
func
countIndent
(
s
string
)
int
{
if
len
(
s
)
==
0
{
return
0
}
// FIXME these rules don't actually implement the python3
// lexing rules which state
//
// Indentation is rejected as inconsistent if a source file
// mixes tabs and spaces in a way that makes the meaning
// dependent on the worth of a tab in spaces; a TabError is
// raised in that case
indent
:=
0
for
_
,
c
:=
range
s
{
switch
c
{
case
' '
:
indent
++
case
'\t'
:
// 012345678901234567
// a b
// a b
// a b
// a b
// a b
// a b
// a b
// ab
// a b
indent
+=
tabSize
-
(
indent
&
(
tabSize
-
1
))
default
:
panic
(
py
.
ExceptionNewf
(
py
.
IndentationError
,
"unexpected indent"
))
}
}
return
indent
}
var
operators
=
map
[
string
]
int
{
// 1 Character operators
"("
:
'('
,
")"
:
')'
,
"["
:
'['
,
"]"
:
']'
,
":"
:
':'
,
","
:
','
,
";"
:
';'
,
"+"
:
'+'
,
"-"
:
'-'
,
"*"
:
'*'
,
"/"
:
'/'
,
"|"
:
'|'
,
"&"
:
'&'
,
"<"
:
'<'
,
">"
:
'>'
,
"="
:
'='
,
"."
:
'.'
,
"%"
:
'%'
,
"{"
:
'{'
,
"}"
:
'}'
,
"^"
:
'^'
,
"~"
:
'~'
,
"@"
:
'@'
,
// 2 Character operators
"!="
:
PLINGEQ
,
"%="
:
PERCEQ
,
"&="
:
ANDEQ
,
"**"
:
STARSTAR
,
"*="
:
STAREQ
,
"+="
:
PLUSEQ
,
"-="
:
MINUSEQ
,
"->"
:
MINUSGT
,
"//"
:
DIVDIV
,
"/="
:
DIVEQ
,
"<<"
:
LTLT
,
"<="
:
LTEQ
,
"<>"
:
LTGT
,
"=="
:
EQEQ
,
">="
:
GTEQ
,
">>"
:
GTGT
,
"^="
:
HATEQ
,
"|="
:
PIPEEQ
,
// 3 Character operators
"**="
:
STARSTAREQ
,
"..."
:
ELIPSIS
,
"//="
:
DIVDIVEQ
,
"<<="
:
LTLTEQ
,
">>="
:
GTGTEQ
,
}
var
tokens
=
map
[
string
]
int
{
// Reserved words
"False"
:
FALSE
,
"None"
:
NONE
,
"True"
:
TRUE
,
"and"
:
AND
,
"as"
:
AS
,
"assert"
:
ASSERT
,
"break"
:
BREAK
,
"class"
:
CLASS
,
"continue"
:
CONTINUE
,
"def"
:
DEF
,
"del"
:
DEL
,
"elif"
:
ELIF
,
"else"
:
ELSE
,
"except"
:
EXCEPT
,
"finally"
:
FINALLY
,
"for"
:
FOR
,
"from"
:
FROM
,
"global"
:
GLOBAL
,
"if"
:
IF
,
"import"
:
IMPORT
,
"in"
:
IN
,
"is"
:
IS
,
"lambda"
:
LAMBDA
,
"nonlocal"
:
NONLOCAL
,
"not"
:
NOT
,
"or"
:
OR
,
"pass"
:
PASS
,
"raise"
:
RAISE
,
"return"
:
RETURN
,
"try"
:
TRY
,
"while"
:
WHILE
,
"with"
:
WITH
,
"yield"
:
YIELD
,
}
var
tokenToString
map
[
int
]
string
// Make tokenToString map
func
init
() {
tokenToString
=
make
(
map
[
int
]
string
,
len
(
operators
)
+
len
(
tokens
)
+
16
)
for
k
,
v
:=
range
operators
{
tokenToString
[
v
]
=
k
}
for
k
,
v
:=
range
tokens
{
tokenToString
[
v
]
=
k
}
tokenToString
[
eof
]
=
"eof"
tokenToString
[
eofError
]
=
"eofError"
tokenToString
[
NEWLINE
]
=
"NEWLINE"
tokenToString
[
ENDMARKER
]
=
"ENDMARKER"
tokenToString
[
NAME
]
=
"NAME"
tokenToString
[
INDENT
]
=
"INDENT"
tokenToString
[
DEDENT
]
=
"DEDENT"
tokenToString
[
STRING
]
=
"STRING"
tokenToString
[
NUMBER
]
=
"NUMBER"
tokenToString
[
FILE_INPUT
]
=
"FILE_INPUT"
tokenToString
[
SINGLE_INPUT
]
=
"SINGLE_INPUT"
tokenToString
[
EVAL_INPUT
]
=
"EVAL_INPUT"
}
// True if there are any open brackets
func
(
x
*
yyLex
)
openBrackets
()
bool
{
return
x
.
bracket
!=
0
||
x
.
parenthesis
!=
0
||
x
.
brace
!=
0
}
// States
const
(
readString
=
iota
readIndent
checkEmpty
checkIndent
parseTokens
checkEof
isEof
)
// A Token with value
type
LexToken
struct
{
token
int
value
py.
Object
pos
ast.
Pos
}
// Convert the yySymType and token into a LexToken
func
newLexToken
(
token
int
,
yylval
*
yySymType
) (
lt
LexToken
) {
lt
.
token
=
token
lt
.
pos
=
yylval
.
pos
if
token
==
NAME
{
lt
.
value
=
py
.
String
(
yylval
.
str
)
}
else
if
token
==
STRING
||
token
==
NUMBER
{
lt
.
value
=
yylval
.
obj
}
else
{
lt
.
value
=
nil
}
return
}
// String a LexToken
func
(
lt
*
LexToken
)
String
()
string
{
name
:=
tokenToString
[
lt
.
token
]
if
lt
.
value
==
nil
{
return
fmt
.
Sprintf
(
"%q (%d) %d:%d"
,
name
,
lt
.
token
,
lt
.
pos
.
Lineno
,
lt
.
pos
.
ColOffset
)
}
return
fmt
.
Sprintf
(
"%q (%d) = %T{%v} %d:%d"
,
name
,
lt
.
token
,
lt
.
value
,
lt
.
value
,
lt
.
pos
.
Lineno
,
lt
.
pos
.
ColOffset
)
}
// An slice of LexToken~s
type
LexTokens
[]
LexToken
// Compare two LexTokens
func
(
as
LexTokens
)
Eq
(
bs
[]
LexToken
)
bool
{
if
len
(
as
)
!=
len
(
bs
) {
return
false
}
for
i
:=
range
as
{
a
:=
as
[
i
]
b
:=
bs
[
i
]
if
a
!=
b
{
return
false
}
}
return
true
}
// String a LexTokens
func
(
lts
LexTokens
)
String
()
string
{
buf
:=
new
(bytes.
Buffer
)
_
,
_
=
buf
.
WriteString
(
"["
)
for
i
:=
range
lts
{
lt
:=
lts
[
i
]
_
,
_
=
buf
.
WriteString
(
"{"
)
_
,
_
=
buf
.
WriteString
(
lt
.
String
())
_
,
_
=
buf
.
WriteString
(
"}, "
)
}
_
,
_
=
buf
.
WriteString
(
"]"
)
return
buf
.
String
()
}
// Queue any remaining DEDENTS
func
(
x
*
yyLex
)
queueDedents
() {
for
i
:=
len
(
x
.
indentStack
)
-
1
;
i
>=
1
;
i
--
{
x
.
queue
(
DEDENT
)
}
x
.
indentStack
=
x
.
indentStack
[:
1
]
}
// The parser calls this method to get each new token. This
// implementation returns operators and NUM.
func
(
x
*
yyLex
)
Lex
(
yylval
*
yySymType
) (
ret
int
) {
// Clear out the yySymType on each token (copied from rsc's cc)
*
yylval
=
yySymType
{}
x
.
yylval
=
yylval
if
yyDebug
>=
2
{
defer
func
() {
lt
:=
newLexToken
(
ret
,
yylval
)
fmt
.
Printf
(
"LEX> %s
\n
"
,
lt
.
String
())
}()
}
// Return queued tokens if there are any
if
!
x
.
queueEmpty
() {
yylval
.
pos
=
x
.
pos
return
x
.
dequeue
()
}
for
{
yylval
.
pos
=
x
.
pos
switch
x
.
state
{
case
readString
:
// Read x.line
x
.
refill
()
yylval
.
pos
=
x
.
pos
x
.
state
++
if
x
.
line
==
""
&&
x
.
eof
{
x
.
state
=
checkEof
// During interactive input of statements an entirely blank logical
// line (i.e. one containing not even whitespace or a comment)
// terminates a multi-line statement.
if
x
.
interactive
&&
!
x
.
openBrackets
() {
x
.
queueDedents
()
x
.
queue
(
NEWLINE
)
return
x
.
dequeue
()
}
continue
}
case
readIndent
:
// Read the initial indent and get rid of it
trimmed
:=
strings
.
TrimLeft
(
x
.
line
,
"
\t
"
)
removed
:=
len
(
x
.
line
)
-
len
(
trimmed
)
x
.
currentIndent
=
x
.
line
[:
removed
]
x
.
pos
.
ColOffset
+=
removed
x
.
line
=
trimmed
x
.
state
++
case
checkEmpty
:
despaced
:=
strings
.
TrimSpace
(
x
.
line
)
// remove other whitespace other than " \t"
// Ignore line if just white space or whitespace then comment
if
despaced
==
""
||
despaced
[
0
]
==
'#'
{
x
.
state
=
checkEof
continue
}
x
.
state
++
case
checkIndent
:
x
.
state
++
// Don't output INDENT or DEDENT if brackets are open
if
x
.
openBrackets
() {
continue
}
// See if indent has changed and issue INDENT / DEDENT
indent
:=
countIndent
(
x
.
currentIndent
)
i
:=
len
(
x
.
indentStack
)
-
1
indentStackTop
:=
x
.
indentStack
[
i
]
if
indent
==
indentStackTop
{
continue
}
else
if
indent
>
indentStackTop
{
x
.
indentStack
=
append
(
x
.
indentStack
,
indent
)
yylval
.
pos
.
ColOffset
=
0
// Indents start at 0
return
INDENT
}
else
{
for
;
i
>=
0
;
i
--
{
if
x
.
indentStack
[
i
]
==
indent
{
goto
foundIndent
}
x
.
queue
(
DEDENT
)
}
x
.
SyntaxError
(
"Inconsistent indent"
)
return
eof
foundIndent:
x
.
indentStack
=
x
.
indentStack
[:
i
+
1
]
return
x
.
dequeue
()
}
case
parseTokens
:
// Skip white space
trimmed
:=
strings
.
TrimLeft
(
x
.
line
,
"
\t
"
)
x
.
pos
.
ColOffset
+=
len
(
x
.
line
)
-
len
(
trimmed
)
x
.
line
=
trimmed
// Peek next word
if
len
(
x
.
line
)
==
0
{
x
.
state
=
checkEof
continue
}
// Check if newline or comment reached
if
x
.
line
[
0
]
==
'\n'
||
x
.
line
[
0
]
==
'#'
{
x
.
state
=
checkEof
// Don't output NEWLINE if brackets are open
if
x
.
openBrackets
() {
continue
}
return
NEWLINE
}
// Check if continuation character
if
x
.
line
[
0
]
==
'\\'
&&
(
len
(
x
.
line
)
<=
1
||
x
.
line
[
1
]
==
'\n'
) {
if
x
.
eof
{
x
.
state
=
checkEof
continue
}
x
.
refill
()
x
.
state
=
parseTokens
continue
}
// Note start of token for parser
yylval
.
pos
=
x
.
pos
// Read a number if available
token
,
value
:=
x
.
readNumber
()
if
token
!=
eof
{
if
token
==
eofError
{
return
eof
}
yylval
.
obj
=
value
return
token
}
// Read a string if available
token
,
value
=
x
.
readString
()
if
token
!=
eof
{
if
token
==
eofError
{
return
eof
}
yylval
.
obj
=
value
return
token
}
// Read a keyword or identifier if available
token
,
str
:=
x
.
readIdentifierOrKeyword
()
if
token
!=
eof
{
yylval
.
str
=
str
return
token
}
// Read an operator if available
token
=
x
.
readOperator
()
if
token
!=
eof
{
// implement implicit line joining rules
switch
token
{
case
'['
:
x
.
bracket
++
case
']'
:
x
.
bracket
--
case
'('
:
x
.
parenthesis
++
case
')'
:
x
.
parenthesis
--
case
'{'
:
x
.
brace
++
case
'}'
:
x
.
brace
--
}
return
token
}
// Nothing we recognise found
x
.
SyntaxError
(
"invalid syntax"
)
return
eof
case
checkEof
:
if
x
.
eof
{
x
.
queueDedents
()
// then return ENDMARKER
x
.
state
=
isEof
if
!
x
.
interactive
{
x
.
queue
(
ENDMARKER
)
}
if
x
.
queueEmpty
() {
continue
}
return
x
.
dequeue
()
}
x
.
state
=
readString
case
isEof
:
return
eof
default
:
panic
(
"Bad state"
)
}
}
}
// Can this rune start an identifier?
//
// identifier: `xid_start` `xid_continue`*
// id_start: <all characters in general categories Lu, Ll, Lt, Lm, Lo, Nl, the underscore, and characters with the Other_ID_Start property>
// id_continue: <all characters in `id_start`, plus characters in the categories Mn, Mc, Nd, Pc and others with the Other_ID_Continue property>
// xid_start: <all characters in `id_start` whose NFKC normalization is in "id_start xid_continue*">
// xid_continue: <all characters in `id_continue` whose NFKC normalization is in "id_continue*">
func
isIdentifierStart
(
c
rune
)
bool
{
switch
{
case
c
>=
'a'
&&
c
<=
'z'
:
return
true
case
c
>=
'A'
&&
c
<=
'Z'
:
return
true
case
c
==
'_'
:
return
true
case
c
<
128
:
return
false
case
unicode
.
In
(
c
,
unicode
.
Lu
,
unicode
.
Ll
,
unicode
.
Lt
,
unicode
.
Lm
,
unicode
.
Lo
,
unicode
.
Nl
):
return
true
}
return
false
}
// Can this rune continue an identifier?
func
isIdentifierChar
(
c
rune
)
bool
{
switch
{
case
c
>=
'a'
&&
c
<=
'z'
:
return
true
case
c
>=
'A'
&&
c
<=
'Z'
:
return
true
case
c
>=
'0'
&&
c
<=
'9'
:
return
true
case
c
==
'_'
:
return
true
case
c
<
128
:
return
false
case
unicode
.
In
(
c
,
unicode
.
Lu
,
unicode
.
Ll
,
unicode
.
Lt
,
unicode
.
Lm
,
unicode
.
Lo
,
unicode
.
Nl
,
unicode
.
Mn
,
unicode
.
Mc
,
unicode
.
Nd
,
unicode
.
Pc
):
return
true
}
return
false
}
// Cut i characters off the start of the line
//
// returns the characters cut
func
(
x
*
yyLex
)
cut
(
i
int
) (
cut
string
) {
cut
,
x
.
line
=
x
.
line
[:
i
],
x
.
line
[
i
:]
x
.
pos
.
ColOffset
+=
i
return
cut
}
// Read an identifier
func
(
x
*
yyLex
)
readIdentifier
()
string
{
var
i
int
var
c
rune
for
i
,
c
=
range
x
.
line
{
if
i
==
0
{
if
!
isIdentifierStart
(
c
) {
goto
found
}
}
else
{
if
!
isIdentifierChar
(
c
) {
goto
found
}
}
}
i
=
len
(
x
.
line
)
found:
return
x
.
cut
(
i
)
}
// Read an identifier or keyword
func
(
x
*
yyLex
)
readIdentifierOrKeyword
() (
int
,
string
) {
identifier
:=
x
.
readIdentifier
()
if
identifier
==
""
{
return
eof
,
""
}
token
,
ok
:=
tokens
[
identifier
]
if
ok
{
return
token
,
identifier
}
return
NAME
,
identifier
}
// Read operator - returns token or eof for not found
func
(
x
*
yyLex
)
readOperator
()
int
{
// Look for length 3, 2, 1 operators
for
i
:=
3
;
i
>=
1
;
i
--
{
if
len
(
x
.
line
)
>=
i
{
op
:=
x
.
line
[:
i
]
if
tok
,
ok
:=
operators
[
op
];
ok
{
x
.
cut
(
i
)
return
tok
}
}
}
return
eof
}
const
pointFloat
=
`([0-9]*\.[0-9]+|[0-9]+\.)`
var
(
decimalInteger
=
regexp
.
MustCompile
(
`^[0-9]+[jJ]?`
)
illegalDecimalInteger
=
regexp
.
MustCompile
(
`^0[0-9]*[1-9][0-9]*$`
)
octalInteger
=
regexp
.
MustCompile
(
`^0[oO][0-7]+`
)
hexInteger
=
regexp
.
MustCompile
(
`^0[xX][0-9a-fA-F]+`
)
binaryInteger
=
regexp
.
MustCompile
(
`^0[bB][01]+`
)
floatNumber
=
regexp
.
MustCompile
(
`^(([0-9]+|`
+
pointFloat
+
`)[eE][+-]?[0-9]+|`
+
pointFloat
+
`)[jJ]?`
)
)
// Read one of the many types of python number
//
// Returns eof for couldn't read number or eofError on a bad read
func
(
x
*
yyLex
)
readNumber
() (
token
int
,
value
py.
Object
) {
// Quick check for this being a number
if
len
(
x
.
line
)
==
0
{
return
eof
,
nil
}
// Starts with a digit
r0
:=
x
.
line
[
0
]
if
'0'
<=
r0
&&
r0
<=
'9'
{
goto
isNumber
}
// Or starts with . then a digit
if
len
(
x
.
line
)
>
1
&&
r0
==
'.'
{
if
r1
:=
x
.
line
[
1
];
'0'
<=
r1
&&
r1
<=
'9'
{
goto
isNumber
}
}
return
eof
,
nil
isNumber:
var
s
string
var
err
error
if
s
=
octalInteger
.
FindString
(
x
.
line
);
s
!=
""
{
value
,
err
=
py
.
IntFromString
(
s
[
2
:],
8
)
if
err
!=
nil
{
panic
(
err
)
}
}
else
if
s
=
hexInteger
.
FindString
(
x
.
line
);
s
!=
""
{
value
,
err
=
py
.
IntFromString
(
s
[
2
:],
16
)
if
err
!=
nil
{
panic
(
err
)
}
}
else
if
s
=
binaryInteger
.
FindString
(
x
.
line
);
s
!=
""
{
value
,
err
=
py
.
IntFromString
(
s
[
2
:],
2
)
if
err
!=
nil
{
panic
(
err
)
}
}
else
if
s
=
floatNumber
.
FindString
(
x
.
line
);
s
!=
""
{
last
:=
s
[
len
(
s
)
-
1
]
imaginary
:=
false
toParse
:=
s
if
last
==
'j'
||
last
==
'J'
{
imaginary
=
true
toParse
=
s
[:
len
(
s
)
-
1
]
}
value
,
err
=
py
.
FloatFromString
(
toParse
)
if
err
!=
nil
{
panic
(
err
)
}
if
imaginary
{
value
=
py
.
Complex
(
complex
(
0
,
value
.(py.
Float
)))
}
}
else
if
s
=
decimalInteger
.
FindString
(
x
.
line
);
s
!=
""
{
last
:=
s
[
len
(
s
)
-
1
]
if
last
==
'j'
||
last
==
'J'
{
toParse
:=
s
[:
len
(
s
)
-
1
]
value
,
err
=
py
.
FloatFromString
(
toParse
)
if
err
!=
nil
{
panic
(
err
)
}
value
=
py
.
Complex
(
complex
(
0
,
value
.(py.
Float
)))
}
else
{
// Discard numbers with leading 0 except all 0s
if
illegalDecimalInteger
.
FindString
(
s
)
!=
""
{
// FIXME where is this error going in the grammar?
x
.
SyntaxError
(
"illegal decimal with leading zero"
)
return
eofError
,
nil
}
value
,
err
=
py
.
IntFromString
(
s
,
10
)
if
err
!=
nil
{
panic
(
err
)
}
}
}
else
{
panic
(
"Unparsed number"
)
}
x
.
cut
(
len
(
s
))
token
=
NUMBER
return
}
// Read one of the many types of python string
//
// May return eof to skip to next matcher, or eofError indicating there was a problem
func
(
x
*
yyLex
)
readString
() (
token
int
,
value
py.
Object
) {
// Quick check for this being a string
if
len
(
x
.
line
)
==
0
{
return
eof
,
nil
}
r0
:=
x
.
line
[
0
]
r1
:=
byte
(
0
)
r2
:=
byte
(
0
)
if
len
(
x
.
line
)
>=
2
{
r1
=
x
.
line
[
1
]
if
len
(
x
.
line
)
>=
3
{
r2
=
x
.
line
[
2
]
}
}
rawString
:=
false
// whether we are parsing a r"" string
byteString
:=
false
// whether we are parsing a b"" string
// u"" strings are just normal strings so we ignore that qualifier
// Start of string
if
r0
==
'\''
||
r0
==
'"'
{
goto
found
}
// Or start of r"" u"" b""
if
(
r0
==
'r'
||
r0
==
'R'
)
&&
(
r1
==
'\''
||
r1
==
'"'
) {
rawString
=
true
x
.
cut
(
1
)
goto
found
}
if
(
r0
==
'b'
||
r0
==
'B'
)
&&
(
r1
==
'\''
||
r1
==
'"'
) {
byteString
=
true
x
.
cut
(
1
)
goto
found
}
if
(
r0
==
'u'
||
r0
==
'U'
)
&&
(
r1
==
'\''
||
r1
==
'"'
) {
x
.
cut
(
1
)
goto
found
}
// Or start of br"" Br"" bR"" BR"" rb"" rB"" Rb"" RB""
if
(
r0
==
'r'
||
r0
==
'R'
)
&&
(
r1
==
'b'
||
r1
==
'B'
)
&&
(
r2
==
'\''
||
r2
==
'"'
) {
rawString
=
true
byteString
=
true
x
.
cut
(
2
)
goto
found
}
if
(
r0
==
'b'
||
r0
==
'B'
)
&&
(
r1
==
'r'
||
r1
==
'R'
)
&&
(
r2
==
'\''
||
r2
==
'"'
) {
rawString
=
true
byteString
=
true
x
.
cut
(
2
)
goto
found
}
return
eof
,
nil
found:
multiLineString
:=
false
stringEnd
:=
""
// Use x.rawString and x.byteString flags
// Parse "x" """x""" 'x' '''x'''
if
strings
.
HasPrefix
(
x
.
line
,
`"""`
) {
stringEnd
=
`"""`
x
.
cut
(
3
)
multiLineString
=
true
}
else
if
strings
.
HasPrefix
(
x
.
line
,
`'''`
) {
stringEnd
=
`'''`
x
.
cut
(
3
)
multiLineString
=
true
}
else
if
strings
.
HasPrefix
(
x
.
line
,
`"`
) {
stringEnd
=
`"`
x
.
cut
(
1
)
}
else
if
strings
.
HasPrefix
(
x
.
line
,
`'`
) {
stringEnd
=
`'`
x
.
cut
(
1
)
}
else
{
panic
(
"Bad string start"
)
}
buf
:=
new
(bytes.
Buffer
)
for
{
escape
:=
false
for
i
,
c
:=
range
x
.
line
{
if
escape
{
// Continuation line - remove \ then continue
if
c
==
'\n'
{
buf
.
Truncate
(
buf
.
Len
()
-
1
)
goto
readMore
}
_
,
_
=
buf
.
WriteRune
(
c
)
escape
=
false
}
else
{
if
strings
.
HasPrefix
(
x
.
line
[
i
:],
stringEnd
) {
x
.
cut
(
i
+
len
(
stringEnd
))
goto
foundEndOfString
}
if
c
==
'\\'
{
escape
=
true
}
if
!
multiLineString
&&
c
==
'\n'
{
break
}
_
,
_
=
buf
.
WriteRune
(
c
)
}
}
if
!
multiLineString
{
x
.
SyntaxErrorf
(
"EOL while scanning string literal"
)
return
eofError
,
nil
}
readMore:
if
x
.
eof
{
if
multiLineString
{
x
.
SyntaxErrorf
(
"EOF while scanning triple-quoted string literal"
)
}
else
{
x
.
SyntaxErrorf
(
"EOL while scanning string literal"
)
}
return
eofError
,
nil
}
x
.
refill
()
}
foundEndOfString:
if
!
rawString
{
var
err
error
buf
,
err
=
DecodeEscape
(
buf
,
byteString
)
if
err
!=
nil
{
x
.
SyntaxErrorf
(
"Decode error: %v"
,
err
)
return
eofError
,
nil
}
}
if
byteString
{
return
STRING
,
py
.
Bytes
(
buf
.
Bytes
())
}
return
STRING
,
py
.
String
(
buf
.
String
())
}
// The parser calls this method on a parse error.
func
(
x
*
yyLex
)
Error
(
s
string
) {
x
.
error
=
true
if
yyDebug
>=
1
{
log
.
Printf
(
"Parse error: %s"
,
s
)
log
.
Printf
(
"Parse buffer %q"
,
x
.
line
)
log
.
Printf
(
"State %#v"
,
x
)
}
}
// The parser calls this method on a parse error.
func
(
x
*
yyLex
)
SyntaxError
(
s
string
) {
x
.
errorString
=
s
x
.
Error
(
s
)
}
// Call this to write formatted errors
func
(
x
*
yyLex
)
SyntaxErrorf
(
format
string
,
a
...
interface
{}) {
x
.
SyntaxError
(
fmt
.
Sprintf
(
format
,
a
...
))
}
// Returns an python error for the current yyLex
func
(
x
*
yyLex
)
ErrorReturn
()
error
{
if
x
.
error
{
if
x
.
errorString
==
""
{
if
x
.
eof
&&
x
.
interactive
{
x
.
errorString
=
"unexpected EOF while parsing"
}
else
{
x
.
errorString
=
"invalid syntax"
}
}
return
py
.
ExceptionNewf
(
py
.
SyntaxError
,
"%s"
,
x
.
errorString
)
}
return
nil
}
// Set the debug level 0 = off, 4 = max
func
SetDebug
(
level
int
) {
yyDebug
=
level
}
// Parse a file
func
Parse
(
in
io.
Reader
,
filename
string
,
mode
string
) (
mod
ast.
Mod
,
err
error
) {
lex
,
err
:=
NewLex
(
in
,
filename
,
mode
)
if
err
!=
nil
{
return
nil
,
err
}
defer
func
() {
if
r
:=
recover
();
r
!=
nil
{
err
=
py
.
MakeSyntaxError
(
r
,
filename
,
lex
.
pos
.
Lineno
,
lex
.
pos
.
ColOffset
,
lex
.
lastLine
)
}
}()
yyParse
(
lex
)
err
=
lex
.
ErrorReturn
()
if
err
!=
nil
{
err
=
py
.
MakeSyntaxError
(
err
,
filename
,
lex
.
pos
.
Lineno
,
lex
.
pos
.
ColOffset
,
lex
.
lastLine
)
}
return
lex
.
mod
,
err
}
// Parse a string
func
ParseString
(
in
string
,
mode
string
) (ast.
Ast
,
error
) {
return
Parse
(
bytes
.
NewBufferString
(
in
),
"<string>"
,
mode
)
}
// Lex a file only, returning a sequence of tokens
func
Lex
(
in
io.
Reader
,
filename
string
,
mode
string
) (
lts
LexTokens
,
err
error
) {
lex
,
err
:=
NewLex
(
in
,
filename
,
mode
)
if
err
!=
nil
{
return
nil
,
err
}
defer
func
() {
if
r
:=
recover
();
r
!=
nil
{
err
=
py
.
MakeSyntaxError
(
r
,
filename
,
lex
.
pos
.
Lineno
,
lex
.
pos
.
ColOffset
,
lex
.
lastLine
)
}
}()
yylval
:=
yySymType
{}
for
{
ret
:=
lex
.
Lex
(
&
yylval
)
if
ret
==
eof
{
break
}
lt
:=
newLexToken
(
ret
,
&
yylval
)
lts
=
append
(
lts
,
lt
)
}
err
=
lex
.
ErrorReturn
()
if
err
!=
nil
{
err
=
py
.
MakeSyntaxError
(
err
,
filename
,
lex
.
pos
.
Lineno
,
lex
.
pos
.
ColOffset
,
lex
.
lastLine
)
}
return
}
// Lex a string
func
LexString
(
in
string
,
mode
string
) (
lts
LexTokens
,
err
error
) {
return
Lex
(
bytes
.
NewBufferString
(
in
),
"<string>"
,
mode
)
}
Back
|
FazBrowse Home
|
New Git URL